Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases centered around desire and preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.17
     Kov
    -0.16
    iki
    -0.16
    å¹¹ç·ļ
    -0.15
    quets
    -0.15
     sever
    -0.15
    zp
    -0.15
    z
    -0.15
    umes
    -0.14
     Revenue
    -0.14
    POSITIVE LOGITS
    venta
    0.16
     Ñģел
    0.16
    iale
    0.15
    iston
    0.15
    apel
    0.15
    oxel
    0.15
    efa
    0.15
    .ut
    0.15
    ÙĬÙĨÙĩ
    0.14
    WithValue
    0.14
    Act Density 0.293%

    No Known Activations